Cover Image

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ling Team, Han, Bin, Tang, Caizhi, Liang, Chen, Zhang, Donghao, Yuan, Fan, Zhu, Feng, Gao, Jie, Hu, Jingyu, Li, Longfei, Li, Meng, Zhang, Mingyang, Jiang, Peijie, Jiao, Peng, Zhao, Qian, Yang, Qingyuan, Shen, Wenbo, Yang, Xinxing, Zhang, Yalin, Ren, Yankun, Zhao, Yao, Cao, Yibo, Sun, Yixuan, Zhang, Yue, Fang, Yuchen, Lin, Zibin, Cheng, Zixuan, Zhou, Jun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Design and Validation of the Digital Receiver System for the next-generation radio interferometer
by: Qu, Donghao, et al.
Published: (2025)

Combining Incomplete Observational and Randomized Data for Heterogeneous Treatment Effects
by: Yao, Dong, et al.
Published: (2024)

Scaling Laws for Code: Every Programming Language Matters
by: Yang, Jian, et al.
Published: (2025)

A Novel Approach for Automated Design Information Mining from Issue Logs
by: Zhao, Jiuang, et al.
Published: (2024)

RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems
by: Liu, Weicong, et al.
Published: (2026)

Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
by: Codefuse, et al.
Published: (2025)

An average-case sensitivity analysis for unmeasured confounding
by: Zhang, Yao, et al.
Published: (2022)

Multiple conditional randomization tests for lagged and spillover treatment effects
by: Zhang, Yao, et al.
Published: (2021)

SpaceOctopus: An Octopus-inspired Motion Planning Framework for Multi-arm Space Robot
by: Zhao, Wenbo, et al.
Published: (2024)

Enhancing Automated Program Repair with Solution Design
by: Zhao, Jiuang, et al.
Published: (2024)

Energy Decay Estimates for the Wave Equation With Logarithmic Feedback
by: Donghao Li, et al.
Published: (2025)

Two-Timescale Dynamic Service Deployment and Task Scheduling with Spatiotemporal Collaboration in Mobile Edge Networks
by: Li, Yang, et al.
Published: (2025)

MMWiLoc: A Multi-Sensor Dataset and Robust Device-Free Localization Method Using Commercial Off-The-Shelf Millimeter Wave Wi-Fi Devices
by: Ding, Wenbo, et al.
Published: (2025)

Exploring Therapeutic Targets From Spreading Patterns Against Respiratory Syncytial Virus
by: Han Zhang, et al.
Published: (2025)

Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models
by: Ling Team, et al.
Published: (2025)

Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts
by: Zhang, Tianyu, et al.
Published: (2024)

Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
by: Zhang, Runze, et al.
Published: (2025)

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing
by: Zhao, Yunze, et al.
Published: (2026)

Recent Advances in Palladium‐Catalyzed Asymmetric Heck/Tsuji–Trost Reactions of 1,n‐Dienes
by: Guofeng Zhao, et al.
Published: (2024)

Genetic Variants Affecting FADS2 Enzyme Dynamics and Gene Expression in Cogenetic Oysters with Different PUFA Levels Provide New Tools to Improve Unsaturated Fatty Acids.
by: Li, Qingyuan, et al.
Published: (2024)

An Artificial Intelligence Framework for Joint Structural-Temporal Load Forecasting in Cloud Native Platforms
by: Zhang, Qingyuan
Published: (2026)

Inductance-Based Force Self-Sensing in Fiber-Reinforced Pneumatic Twisted-and-Coiled Actuators
by: Zhang, Yunsong, et al.
Published: (2026)

FIGURE 5 in Taxonomy of the leafhopper genus Limentinus (Hemiptera: Cicadellidae: Coelidiinae) with description of three new species from Madagascar
by: Jin, Mengyuan, et al.
Published: (2026)

FIGURE 3 in Taxonomy of the leafhopper genus Limentinus (Hemiptera: Cicadellidae: Coelidiinae) with description of three new species from Madagascar
by: Jin, Mengyuan, et al.
Published: (2026)

A Review of Advanced Processing Technologies for Birefringent Cellulosic Anti‐Counterfeiting Materials
by: Jin Lv, et al.
Published: (2024)

Data-Efficient and Robust Trajectory Generation through Pathlet Dictionary Learning
by: Tang, Yuanbo, et al.
Published: (2025)

Universal Online Convex Optimization with $1$ Projection per Round
by: Yang, Wenhao, et al.
Published: (2024)

FIGURE 8 in Notes of the leafhopper genus Mitjaevia Dworakowska from China (Hemiptera: Cicadellidae: Typhlocybinae), with descriptions of eight new species
by: Yang, Meixia, et al.
Published: (2025)

FIGURE 13. Mitjaevia wangwushana Song, Li in Notes of the leafhopper genus Mitjaevia Dworakowska from China (Hemiptera: Cicadellidae: Typhlocybinae), with descriptions of eight new species
by: Yang, Meixia, et al.
Published: (2025)

FIGURE 9. Mitjaevia protuberanta Song, Li in Notes of the leafhopper genus Mitjaevia Dworakowska from China (Hemiptera: Cicadellidae: Typhlocybinae), with descriptions of eight new species
by: Yang, Meixia, et al.
Published: (2025)

Mitjaevia mianningensis Yang & Cao & Zhang 2025, sp. nov.
by: Yang, Meixia, et al.
Published: (2025)

Conditioning Matters: Training Diffusion Policies is Faster Than You Think
by: Dong, Zibin, et al.
Published: (2025)

A‐D‐A Structured Molecular Fillers for Boosting High‐Temperature Insulation of Polymer Dielectrics
by: Jie Li, et al.
Published: (2026)

Discovery of novel STAT3 inhibitors with anti-breast cancer activity: structure-based virtual screening, molecular dynamics and biological evaluation.
by: Wang, Jinhui, et al.
Published: (2025)

A Multimodal Neurophysiological Framework for Real‐Time Evaluation of User Experience in Virtual Architectural Environments
by: Hui Liang, et al.
Published: (2026)

YbNi$_4$Mg: Superheavy fermion with enhanced Wilson ratio and magnetocaloric effect
by: Zhang, Xiaoci, et al.
Published: (2024)

Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport
by: Zhang, Zhenyi, et al.
Published: (2024)

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation
by: Ling Team, et al.
Published: (2025)

A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
by: Lu, Jingyu, et al.
Published: (2025)

TraceTrans: Translation and Spatial Tracing for Surgical Prediction
by: Luo, Xiyu, et al.
Published: (2025)